Autonomous AI agents that perform tasks independently
assafkip
Open-source, self-hosted OSINT investigation platform: turn documents into a live, investigated entity graph. Autonomous agent, graph analytics (centrality, communities, pathfinding), keyless-first tool belt.
...morehuangji6693-max
The behavioral operating system for Claude Code agents — distilled from 11 deeply-read libraries (179 skills + 99 agents + Karpathy 4 laws + memory architecture). Drop-in rules, scripts, and curated catalog.
...morejordanrburger
Autonomous daily briefing for Claude Code that cross-checks Slack, Gmail, Calendar, Linear & GitHub — so nothing falls through the cracks, and you can trust what it surfaces.
...moreMaggy Contributors
Maggy — a local AI engineering command center: multi-model routing, intent graph, memory, and a web dashboard for Claude Code.
...moreObservability and proof reporting for AI agents
tcconnally
Trace cross-file dependency blast radius with GitLab Orbit, before you break things.
AgentCulture
culture-agent-template — a clonable template for AgentCulture mesh agents.
"MLDSAI Inc." <[email protected]>
Model-agnostic, domain-agnostic ML engine for GUI automation agents
UnaryLab
Install the ai-for-research Agent Skills into a coding agent's skills directory.
Constructive <[email protected]>
LLM integration plugin for PostGraphile v5 — server-side text-to-vector embedding and text companion fields for pgvector columns
...moreWhatsApp Sales SaaS SDK — autonomous WA agent (Kapso + Hindsight RAG + Honcho memory + OpenRouter)
Microsoft Agent Framework conversation history backed by PerSQL — durable message history in an isolated SQLite database per agent.
...morequinton_miller
Trusted-actions executor: approval gateway, push notifications, execution runner, Playwright adapters. HITL gateway for agent-driven purchases and other risky actions.
...morepvhee
Turn a folder of JSON into an installable, offline-first practice app. The mill that grinds questions into knowledge.
hellblazer
Stateful MCP supervisor exposing Qwen Code as a multi-backend agent — see docs/rdr/RDR-001
cryptosuess
The Operating System for AI Security — monitor, secure, and audit every AI agent and LLM application in production. Zero-dependency telemetry, redaction, and firewall SDK for Canary.
...moremichael-pr
Run and manage QA Wolf flows from the terminal, CI, or an AI agent
Bernier LLC
Framework-agnostic streaming agent loop for multi-turn LLM tool-call orchestration
Vedant Singh <[email protected]>
Safety Infrastructure for AI Agents - Tool dependencies, channel integrity, and runtime protection
NeuronKnight <[email protected]>
CVE-style advisory database and static scanner for AI agent security risks
tcconnally
Shared memory and tool layer for Perseus agents — MemoryEntry, Elastic/Engram backends, decision log, knowledge graph, project context.
...moreDave Robb
Structured AI-assisted development framework with plan lifecycle, review gates, and continuous improvement.
AgentLedger Python SDK — track, attribute, and govern AI agent spend across OpenAI, Anthropic, and Gemini.
Vercel Sandbox integration for Deep Agents